Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76444
    Prev
    Next
    INDEX
    Explanations

    terms related to furniture and home improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cop
    -0.07
     Guar
    -0.07
    eyer
    -0.07
    edu
    -0.06
    ettle
    -0.06
    hr
    -0.06
    itz
    -0.06
    ÙĪØŃ
    -0.06
     helt
    -0.06
    /Dk
    -0.06
    POSITIVE LOGITS
    PERT
    0.07
    exus
    0.06
    AtA
    0.06
    SWG
    0.06
    reative
    0.06
     ideas
    0.06
    'l
    0.06
     Morr
    0.06
    inel
    0.06
    iram
    0.06
    Activations Density 0.006%

    No Known Activations